Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1808 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.9620. Min Act: -0.0001

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.9655. Min Act: -0.0001

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.6579. Min Act: -0.0001

Data Index: 40883 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.6293. Min Act: -0.0001

Data Index: 591013 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.6266. Min Act: -0.0001

Data Index: 408248 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.5436. Min Act: -0.0001

Data Index: 1057656 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.5550. Min Act: -0.0001

Data Index: 1275775 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.6036. Min Act: -0.0001

Data Index: 1153287 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.4866. Min Act: -0.0001

Data Index: 1052076 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.5272. Min Act: -0.0001

Data Index: 1356815 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.4734. Min Act: -0.0001

Data Index: 1115494 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.5052. Min Act: -0.0001

Data Index: 108421 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.3924. Min Act: -0.0001

Data Index: 1359807 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.4727. Min Act: -0.0001

Data Index: 820227 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.5624. Min Act: -0.0001

Data Index: 595721 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.5002. Min Act: -0.0001

Data Index: 985468 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.4890. Min Act: -0.0001

Data Index: 336567 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.4024. Min Act: -0.0001

Data Index: 543112 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.4408. Min Act: -0.0001

Data Index: 95337 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.4324. Min Act: -0.0001

Data Index: 139855 (C4 (Web Text))

Max Activating Token Index: 302